Unverified50% confidenceFactExact time
Axial attention decomposes attention into two steps: first attention along the spatial axis (electrode dimension), then attention along the temporal axis; both steps have linear complexity, avoiding the quadratic cost of joint spatio-temporal attention.
1
Sources
50%
Confidence
Long-term
Relevance
11/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHybrid architectures (linear attention + standard attention) are more efficient than pure full attention on long-context tasks, but linear attention may be slightly inferior to standard attention on certain reasoning tasks that require precise global dependencies78% similarUnverified自注意力使任意两个位置之间的信息交互只需一步计算,但显存占用随序列长度平方增长78% similarUnverifiedSolutions for streaming processing include causal attention masking, chunked attention, and look-ahead buffering77% similarUnverifiedThe parietal cortex plays the role of spatial integration and attentional orienting.76% similarUnverifiedExisting mainstream sparse attention methods filter interactions by retaining entries with larger values or high-quality regions in the attention matrix.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1157917API
curl https://kongchang.com/api/v1/knowledge/claims/1157917MCP
get_claim(id=1157917)